CNN_Datasets_20210411

This dataset contains 1,523 samples, mostly of white plaster sculptures. There are 30 images in total: 28 fringe images and 2 speckle images. The fringe images have frequencies of 1, 4, 20, 61, 70, and 80 (doubled). The first five frequencies use a 4-step phase-shifting algorithm, and the last one uses an 8-step phase-shifting algorithm. The dataset also includes calibration data for the system and camera. If you want to use the calibration details to reconstruct 3D or depth information, please reach out to us:Hieu Nguyen, PhD: [e-mail] Wang, PhD: [e-mail] you use this dataset in your research, please consider citing our related publications.H. Nguyen, Y. Wang, and Z. Wang, "Single-Shot 3D Shape Reconstruction Using Structured Light and Deep Convolutional Neural Networks," Sensors 20, 3718, 2020.H. Nguyen and Z. Wang, "Accurate 3D Shape Reconstruction from Single Structured-Light Image via Fringe-to-Fringe Network," Photonics 8, 459, 2021.H. Nguyen, E. Novak, and Z. Wang, "Accurate 3D reconstruction via fringe-to-phase network," Measurement 190, 110663, 2022.AH. Nguyen, K. Ly, C. Li, and Z. Wang, "Single-shot 3D shape acquisition using a learning-based structured light technique," Appl. Opt. 61, 8589-8599, 2022.AH. Nguyen, O. Rees, and Z. Wang, "Learning-based 3D imaging from single structured-light image," Graph. Models 126, 101171, 2023.A.H. Nguyen, K. Ly, V.K. Lam, and Z. Wang, "Generalized fringe-to-phase framework for single-shot 3D reconstruction integrating structured light with deep learning," Sensors 23, 4209, 2023.A.H. Nguyen and Z. Wang, "Single-shot 3D Reconstruction via nonlinear Fringe Transformation: Supervised and Unsupervised Learning Approaches," Sensors 24, 3246, 2024.